© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 5802
    Prev
    Next
    INDEX
    Explanations

    named entities that are people, especially drivers

    oai_token-act-pair · gemini-2.0-flash

    Racing context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.75
    Personensuche
    -0.65
    RACE
    -0.65
     race
    -0.60
    race
    -0.59
     '\\;'
    -0.59
    Race
    -0.57
     RACE
    -0.56
    LookAnd
    -0.56
     races
    -0.56
    POSITIVE LOGITS
     balles
    0.54
    بوابة
    0.50
    GGLE
    0.48
    handleClose
    0.46
     ball
    0.45
    Hướng
    0.43
    CardHeader
    0.43
    tagHelperRunner
    0.43
    dsl
    0.43
    nová
    0.42
    Activations Density 18.748%

    No Known Activations